frame-macos-notification
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions specify that the agent should use user-provided content for the title and body of the generated notification.
- Ingestion points: User input as described in SKILL.md and demonstrated in example.md.
- Boundary markers: Absent. No instructions are provided to the agent to use delimiters or ignore embedded code in the user's text.
- Capability inventory: Generates HTML/CSS intended for rendering in a browser context.
- Sanitization: Absent. The skill does not provide instructions to escape HTML characters or validate the input, creating a potential cross-site scripting (XSS) vector if the input contains malicious scripts.
- [EXTERNAL_DOWNLOADS]: The generated HTML output references external resources from well-known services.
- Evidence: The template in example.html loads the Tailwind CSS utility library from cdn.tailwindcss.com and typography from fonts.googleapis.com.
Audit Metadata